Text-to-Video Generation on MSR-VTT (zero-shot)
212FVDReCo
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| ReCoParams=7B, zero-shot=true2026.04 | 212 | 30.56 | — | 1 | |
| ReCo*Params=7B, zero-shot=true2026.04 | 267 | 29.11 | — | 0.5 | |
| LoongParams=7B, zero-shot=true2026.04 | 274 | 29.03 | — | 1 | |
| MicroCinematraining_data_source=WebVid-10M only, zero-shot=true2023.11 | 377.4 | 29.67 | — | — | |
| CAT-LVDM (BCNI)#Params=∼2.3B, #Videos (train)=∼2M2025.05 | 396.3 | — | — | — | |
| DEMO#Params=∼2.3B, #Videos (train)=∼10M2025.05 | 422 | — | — | — | |
| CAT-LVDM (SACN)#Params=∼2.3B, #Videos (train)=∼2M2025.05 | 440.3 | — | — | — | |
| Gaussian#Params=∼2.3B, #Videos (train)=∼2M2025.05 | 445.3 | — | — | — | |
| SimDAtraining_data_source=WebVid-10M only, zero-shot=true2023.11 | 456 | 29.45 | — | — | |
| VideoComposer#Params=∼1.7B, #Videos (train)=∼10M2025.05 | 456 | — | — | — | |
| FreeNoise#Params=∼1.7B, #Videos (train)=∼10M2025.05 | 517 | — | — | — | |
| Uniform#Params=∼2.3B, #Videos (train)=∼2M2025.05 | 526.8 | — | — | — | |
| ModelScopeT2V (Finetuned)#Params=∼1.7B, #Videos (train)=∼10M2025.05 | 536 | — | — | — | |
| Show-1training_data_source=WebVid-10M only, zero-shot=true2023.11 | 538 | 30.72 | — | — | |
| Show-1#Params=∼6B, #Videos (train)=∼10M2025.05 | 538 | — | — | — | |
| ModelScopetraining_data_source=WebVid-10M and additional data, zero-shot=true2023.11 | 550 | 29.3 | — | — | |
| SimDA#Params=∼1.1B, #Videos (train)=∼10M2025.05 | 550 | — | — | — | |
| VideoFusion#Params=∼2.59B, #Videos (train)=∼10M2025.05 | 550 | — | — | — | |
| ModelScopeT2V#Params=∼1.7B, #Videos (train)=∼10M2025.05 | 557 | — | — | — | |
| VideoComposertraining_data_source=WebVid-10M only, zero-shot=true2023.11 | 580 | 29.32 | — | — | |
| VideoFusiontraining_data_source=WebVid-10M only, zero-shot=true2023.11 | 581 | 27.95 | — | — | |
| PEEKABOO#Params=∼1.7B, #Videos (train)=∼10M2025.05 | 609 | — | — | — | |
| LVDMtraining_data_source=WebVid-10M only, zero-shot=true2023.11 | 742 | 23.81 | — | — | |
| MagicVideotraining_data_source=WebVid-10M only, zero-shot=true2023.11 | 998 | — | — | — | |
| MagicVideo#Params=∼1.2B, #Videos (train)=∼17M2025.05 | 998 | — | — | — | |
| CogVideotraining_data_source=WebVid-10M only, zero-shot=true2023.11 | 1,294 | 26.31 | — | — | |
| CogVideo (Chinese)Zero-Shot=true2024.01 | — | 26.14 | 24.78 | — | |
| CogVideo (English)Zero-Shot=true2024.01 | — | 26.31 | 23.59 | — | |
| GODIVAZero-Shot=false2024.01 | — | 24.02 | — | — | |
| Lavietraining_data_source=WebVid-10M and additional data, zero-shot=true2023.11 | — | 29.49 | — | — | |
| Make-A-Videotraining_data_source=WebVid-10M and additional data, zero-shot=true2023.11 | — | 30.49 | — | — | |
| Make-A-VideoZero-Shot=true2024.01 | — | 30.49 | 13.17 | — | |
| NÜWAZero-Shot=false2024.01 | — | 24.39 | 47.68 | — | |
| PYoCotraining_data_source=WebVid-10M and additional data, zero-shot=true2023.11 | — | 32.04 | — | — | |
| PYoCoZero-Shot=true2024.01 | — | — | 10.21 | — | |
| ShowMakerZero-Shot=true2024.01 | — | 29.08 | 12.67 | — | |
| Video LDMtraining_data_source=WebVid-10M only, zero-shot=true2023.11 | — | 29.29 | — | — | |
| Video LDMZero-Shot=true2024.01 | — | 29.29 | — | — | |
| VideoFactorytraining_data_source=WebVid-10M and additional data, zero-shot=true2023.11 | — | 30.05 | — | — |